diff --git a/.VERSION b/.VERSION index e4610d0d7..7dff5b892 100644 --- a/.VERSION +++ b/.VERSION @@ -1 +1 @@ -0.2.1a0 \ No newline at end of file +0.2.1 \ No newline at end of file diff --git a/allenact/algorithms/onpolicy_sync/engine.py b/allenact/algorithms/onpolicy_sync/engine.py index 178a0434a..e06aca5a2 100644 --- a/allenact/algorithms/onpolicy_sync/engine.py +++ b/allenact/algorithms/onpolicy_sync/engine.py @@ -411,12 +411,12 @@ def act(self, rollouts: RolloutStorage): rollouts.masks[rollouts.step : rollouts.step + 1], ) - # Assume actions do not contain a step dimension - actions = ( - actor_critic_output.distributions.sample() - if not self.deterministic_agents - else actor_critic_output.distributions.mode() - ) + # Assume actions do not contain a step dimension + actions = ( + actor_critic_output.distributions.sample() + if not self.deterministic_agents + else actor_critic_output.distributions.mode() + ) return actions, actor_critic_output, memory, step_observation